© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158982
    Prev
    Next
    INDEX
    Explanations

    want to

    np_acts-logits-general · gemini-2.5-flash-lite

    word applies to something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    जित
    0.54
     آئی
    0.50
    姫
    0.50
     солне
    0.50
    𝘈
    0.49
    सबसे
    0.49
     הו
    0.48
    이지만
    0.46
    𝐾
    0.46
    ただ
    0.46
    POSITIVE LOGITS
    lers
    0.54
    en
    0.54
     Streets
    0.54
    aid
    0.52
    iss
    0.52
    marking
    0.52
    iq
    0.51
    atic
    0.51
    ee
    0.51
    iet
    0.51
    Activations Density 0.001%

    No Known Activations